{"record": {"aliases": [], "artifacts": [{"id": "arxiv:2606.20146", "kind": "paper", "url": "https://arxiv.org/abs/2606.20146"}], "authors": ["Bharathi Kannan Nithyanantham", "Clemens Kujat", "Tobias Sesterhenn", "Stefan Telgmann", "Ashwin Nedungadi", "Jörn Plönnigs", "Christian Bartelt", "Stefan Lüdtke"], "authors_reference": {"basis": "arxiv_metadata", "retrieved_at": "2026-11-03", "source_key": "claire-radar:2606.20146", "source_url": "https://arxiv.org/abs/2606.20146"}, "categories": ["General AI", "Language & Knowledge", "cs.AI"], "description": {"en": "BIM-Edit evaluates large language models on natural-language editing of Industry Foundation Classes (IFC) building models. The benchmark includes 324 editing tasks across 11 realistic building models and 36 synthetic scenes. Tasks are categorized as direct, spatial, or topological instructions, and outputs are scored on geometric accuracy, semantic validity, and topological consistency."}, "documents": [{"document_type": "registry_page", "id": "claire_radar:https://arxiv.org/abs/2606.20146", "source": "claire_radar", "source_url": "https://arxiv.org/abs/2606.20146", "title": "BIM-Edit"}], "evidence_summary": {"document_count": 1, "model_count": null, "model_count_basis": null}, "key": "claire-radar:2606.20146", "modality": null, "name": "BIM-Edit", "openness": {"code_license": null, "data_license": null, "evidence": [], "status": "unknown"}, "provenance": {"confidence": "High", "crawl_bundle": "claire_radar_2026-10-14", "crawled_at": "2026-10-14T09:44:51Z", "data_status": "primary-source-indexed", "display_eligible": "unknown", "origin_record_id": "bm_bim-edit_44064775", "origin_source": "arxiv", "recognition_confidence": "1.0", "record_sha256": "622110a322795dbb1b5dd5ef06e4e0db4dc0a560d0935a7946e80a169ca0069e", "relation": "introduces", "review_state": "unreviewed", "source_url": "https://arxiv.org/abs/2606.20146"}, "publisher": null, "released": "2026-06-18", "released_reference": {"basis": "benchmark_release", "source_key": "claire-radar:2606.20146", "source_url": "https://arxiv.org/abs/2606.20146"}, "schema_version": 1, "sizes": [], "slug": "claire-radar-2606-20146", "source": "claire_radar", "source_benchmark_id": "2606.20146", "source_metadata": {"claire_radar": {"adoption30d": null, "aliases": [], "annotation": "Machine Generated", "applicationDomains": ["General AI"], "area": "Language & Knowledge", "attention": {"asOf": "2026-10-05", "attemptedAt": "2026-10-04T15:31:48.030916Z", "githubRepo": null, "githubScope": null, "githubStars": null, "hfDailySubmittedAt": null, "hfDataset": null, "hfDatasetDownloads": null, "hfDatasetLikes": null, "hfPaperUpvotes": null, "hfPaperUrl": "https://huggingface.co/papers/2606.20146", "observedAt": "2026-10-04T03:02:42.754940Z", "signalStatus": {"githubStars": {"state": "not_applicable"}, "hfDatasetDownloads": {"state": "not_applicable"}, "hfDatasetLikes": {"state": "not_applicable"}, "hfPaperUpvotes": {"checkedAt": "2026-10-04T15:31:48.030916Z", "state": "unavailable"}}, "status": "unavailable"}, "capabilities": [], "confidence": "High", "construction": "Original Synthetic", "constructionDetail": "Unknown — the indexer does not infer construction details without explicit source evidence.", "copyGeneration": {"generatedAt": "2026-08-20T15:22:10.044731Z", "inputHash": "a0d8c53ce91c5b0295325792708c88fde7f7f4ec7fe0c3ae31b4181e646ddc89", "model": "deepseek-v4-flash"}, "dataStatus": "primary-source-indexed", "demo": false, "description": "BIM-Edit evaluates large language models on natural-language editing of Industry Foundation Classes (IFC) building models. The benchmark includes 324 editing tasks across 11 realistic building models and 36 synthetic scenes. Tasks are categorized as direct, spatial, or topological instructions, and outputs are scored on geometric accuracy, semantic validity, and topological consistency.", "domainCuration": {"method": "rules-v1", "state": "auto"}, "evidence": {"reasonCodes": ["exact coined title identity tied to benchmark evidence", "benchmark release stated in one sentence", "evaluation protocol evidence"], "snippet": "We introduce BIM-Edit, a benchmark for evaluating LLMs on natural-language editing of Building Information Models (BIM) represented in the Industry Foundation Classes (IFC) format."}, "familyId": "bmf_2a8fff911c4c", "firstSeenAt": "2026-08-19", "githubIndex": {"candidateCount": 0, "indexedAt": "2026-09-17T04:40:34.111665+00:00", "repositories": [], "status": "not-found"}, "heat": null, "id": "bm_bim-edit_44064775", "indexedAt": "2026-08-19T11:05:13.395391Z", "industrySectors": [], "links": {"code": null, "data": null, "hfPaper": "https://huggingface.co/papers/2606.20146", "paper": "https://arxiv.org/abs/2606.20146", "pdf": "https://arxiv.org/pdf/2606.20146", "project": null, "report": "https://arxiv.org/abs/2606.20146"}, "metrics": [], "motivation": "Large language models (LLMs) are increasingly applied to computer-aided design (CAD) to generate design artifacts from textual instructions.", "name": "BIM-Edit", "oneLine": "BIM-Edit evaluates large language models on natural-language editing of Industry Foundation Classes (IFC) building models. The benchmark includes 324 editing tasks across 11 realistic building models and 36 synthetic scenes. Tasks are categorized as direct, spatial, or topological instructions, and outputs are scored on geometric accuracy, semantic validity, and topological consistency.", "paperTitle": "BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling", "primaryDomain": "General AI", "publication": {"evidence": null, "evidenceLevel": "unverified", "evidenceUrl": "https://arxiv.org/abs/2606.20146", "source": "arxiv-metadata", "status": "unverified", "venue": null, "verifiedAt": "2026-10-14T01:46:58.058199Z"}, "publications": [], "ranking": {}, "readiness": "Paper only", "recognitionConfidence": 1.0, "relation": "introduces", "releasedAt": "2026-06-18", "source": {"authors": ["Bharathi Kannan Nithyanantham", "Clemens Kujat", "Tobias Sesterhenn", "Stefan Telgmann", "Ashwin Nedungadi", "J\\\"orn Pl\\\"onnigs", "Christian Bartelt", "Stefan L\\\"udtke"], "categories": ["cs.AI"], "id": "2606.20146", "title": "BIM-Edit: Benchmarking Large Language Models for IFC-Based Building Information Modeling", "type": "arxiv", "url": "https://arxiv.org/abs/2606.20146"}, "sourceUpdatedAt": "2026-06-23T06:59:35Z", "topics": ["cs.AI"], "venueAttempts": [], "whyItMatters": "Construction and architectural design rely on structured BIM models; the evaluation gap is that existing benchmarks mostly test geometry and creation from scratch. BIM-Edit measures scene understanding and semantic relational preservation, providing a capability signal for practical engineering workflows where editing is central."}}}, "schema_version": 1, "scores_by_source": {}, "siblings": []}
